© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 3-GEMMASCOPE-RES-16K
    11. 6099
    Prev
    Next
    INDEX
    Explanations

    URLs or web domain names

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_3/width_16k/average_l0_90
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Италијани
    -1.03
    Tikang
    -0.80
     autorytatywna
    -0.80
    Diweddarwch
    -0.76
    exitRule
    -0.75
    RenderAtEndOf
    -0.71
     ویکی‌پدی
    -0.71
    verifyException
    -0.70
    PreInfinity
    -0.69
    featureID
    -0.69
    POSITIVE LOGITS
    net
    0.38
    http
    0.35
    raborty
    0.35
    {}{}
    0.35
     نی
    0.35
     website
    0.34
     Bastard
    0.33
     inilah
    0.33
     דבר
    0.33
    vergleich
    0.32
    Activations Density 0.116%

    No Known Activations